Air Pollution Monitoring, and Modelling: An Overview

Abstract

Air Pollution has been an eclectic ecological problem exposed and exaggerated by constant urbanization, massive industrialization, population explosion, and unregulated exploitation of resources, which has been affecting both the flora and fauna for far too long. So, a need has arisen in the past few decades to monitor, predict, and finally provide scientific control measures for Air Pollution. The primary focus of this review is on the changing trends in Air Quality research over time and assess where the research stands now in the giant scheme of things regarding Air Pollution. Many modern techniques have been employed in its study, both at the academic and research level, such as the usage of satellite-based atmospheric imagery and datasets, high-resolution sensing systems, and deep learning analysis techniques, which have amplified the research in this field. From manual monitoring to ground-based local sensors, to now advanced high-resolution space-based satellite monitoring and the usage of different kinds of computational intelligence/soft-computing techniques for analysis, forecasting, and modelling, giant leaps have been made in this research field. Recent research is focused on cumulating data availability, including geospatial datasets, deep learning, advanced statistical modelling, and cloud computing platforms in air pollution and environmental studies. In this review, a comprehensive analysis of current and previous studies of air pollution is conducted to give a basic idea about the problem, and the sciences of its monitoring and modelling and different techniques available at its disposal, such as computer simulations, data analytics and computing techniques. Finally, a brief critical analysis of past research, methodologies, present trends, emerging challenges and future research directions are discussed.

Keywords:

• Air quality
• air pollution dynamics
• air quality model
• remote sensing
• deep learning

Acknowledgments

This work would not have been possible without the invaluable discussions and paramount suggestions from my colleagues including Mohammad Aasif Khaja, Farah Amin Beigh, Waseem Ghani and others.

Disclosure Statement

Authors declare no conflict of interest and have all made substantial contributions towards this work.

Data availability statement

No datasets were generated or analyzed during the current study.